Model comparison
Qwen2.5 72B Instruct vs Step 3
Step 3 is the stronger model overall, scoring 39.9 to 31.5 on the Noometry Index.
Last verified . 15 shared benchmarks.
Alibaba (Qwen)
StepFunSummary
- They share 15 benchmarks with published results for both. Qwen2.5 72B Instruct scores higher in 0 categories and Step 3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Step 3 leads 34.9 to 18.1.
Side by side
| Qwen2.5 72B Instruct | Step 3 | |
|---|---|---|
| Provider | Alibaba (Qwen) | StepFun |
| Noometry Index | 31.5 | 39.9 |
| Released | 2024-09 | — |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 8K | — |
| Input $ / M tokens | $1.40 | — |
| Output $ / M tokens | $5.60 | — |
| Results tracked | 43 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3 leads
Qwen2.5 72B Instruct: 32.8 (#256), Step 3: 39.5 (#144)
| Benchmark | Qwen2.5 72B Instruct | Step 3 |
|---|---|---|
| LMArena Coding | 1293 | 1367 |
| WeirdML | 16% | — |
| BigCodeBench Instruct | 45.8% | — |
| BigCodeBench Complete | 55.9% | — |
Agentic & Tool Use Not comparable
Qwen2.5 72B Instruct: 22.0 (#124), Step 3: —
| Benchmark | Qwen2.5 72B Instruct | Step 3 |
|---|---|---|
| TheAgentCompany | 5.7% | — |
| BALROG | 16.2% | — |
| METR Time Horizons | 35.8% | — |
Reasoning Step 3 leads
Qwen2.5 72B Instruct: 21.4 (#197), Step 3: 27.6 (#102)
| Benchmark | Qwen2.5 72B Instruct | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1271 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |
| DTBench | 62.9% | — |
| LMCA | 13.4% | — |
| BIG-Bench Hard | 79.8% | — |
| Epoch Capabilities Index | 129.01 | — |
| ForecastBench | 57.5 | — |
| HellaSwag | 84.8% | — |
| PIQA | 82.6% | — |
| WinoGrande | 82.3% | — |
Math Step 3 leads
Qwen2.5 72B Instruct: 18.1 (#281), Step 3: 34.9 (#148)
| Benchmark | Qwen2.5 72B Instruct | Step 3 |
|---|---|---|
| LMArena Math | 1283 | 1366 |
| OTIS Mock AIME 2024-2025 | 8.1% | — |
| Omni-MATH | 33% | — |
| MATH Level 5 | 63.2% | — |
Knowledge Step 3 leads
Qwen2.5 72B Instruct: 26.9 (#247), Step 3: 36.2 (#161)
| Benchmark | Qwen2.5 72B Instruct | Step 3 |
|---|---|---|
| LMArena Expert | 1245 | 1333 |
| GPQA Diamond | 49.1% | — |
| MMLU-Pro | 63.1% | — |
| Confabulations | 19.1% | — |
| GPQA (HELM) | 42.6% | — |
| ARC (AI2) Challenge | 94.5% | — |
| MMLU | 85.3% | — |
| TriviaQA | 71.9% | — |
Multimodal Not comparable
Qwen2.5 72B Instruct: —, Step 3: 34.9 (#81)
| Benchmark | Qwen2.5 72B Instruct | Step 3 |
|---|---|---|
| LMArena Vision | — | 1176 |
Multilingual Step 3 leads
Qwen2.5 72B Instruct: 41.2 (#208), Step 3: 46.5 (#154)
| Benchmark | Qwen2.5 72B Instruct | Step 3 |
|---|---|---|
| LMArena Non-English | 1252 | 1327 |
| LMArena Chinese | 1272 | 1396 |
| LMArena German | 1234 | 1371 |
| LMArena Korean | 1188 | 1271 |
| LMArena Russian | 1264 | 1331 |
| LMArena Spanish | 1255 | 1372 |
| LMArena French | 1279 | — |
| LMArena Japanese | 1180 | — |
Instruction Following Step 3 leads
Qwen2.5 72B Instruct: 65.7 (#216), Step 3: 70.6 (#159)
| Benchmark | Qwen2.5 72B Instruct | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1254 | 1332 |
| IFEval | 80.6% | — |
Long Context Step 3 leads
Qwen2.5 72B Instruct: 38.9 (#183), Step 3: 40.3 (#152)
| Benchmark | Qwen2.5 72B Instruct | Step 3 |
|---|---|---|
| LMArena Longer Query | 1282 | 1326 |
Writing & Preference Step 3 leads
Qwen2.5 72B Instruct: 46.9 (#210), Step 3: 54.5 (#146)
| Benchmark | Qwen2.5 72B Instruct | Step 3 |
|---|---|---|
| LMArena Text | 1269 | 1351 |
| LMArena Creative Writing | 1221 | 1322 |
| LMArena Multi-Turn | 1272 | 1340 |
| WildBench | 80.2% | — |
Frequently asked questions
Is Qwen2.5 72B Instruct better than Step 3?
Step 3 is the stronger model overall, scoring 39.9 to 31.5 on the Noometry Index.
Is Qwen2.5 72B Instruct or Step 3 better for coding?
Step 3 scores higher on coding benchmarks: 39.5 versus 32.8 in the Noometry coding category.
How many benchmarks do Qwen2.5 72B Instruct and Step 3 share?
15 benchmarks have published results for both models. Qwen2.5 72B Instruct has 43 scored results on Noometry and Step 3 has 17.